© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3057
    Prev
    Next
    INDEX
    Explanations

    say "prototype"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ọng
    -18.25
    腿
    -17.38
    -legged
    -16.00
    utas
    -15.94
    发行
    -14.75
    вит
    -14.63
     Publié
    -14.56
     Policies
    -14.31
     legs
    -14.13
    anism
    -14.13
    POSITIVE LOGITS
     prototype
    69.50
    原型
    65.00
     Prot
    64.50
     prot
    63.75
    prototype
    63.50
     prototypes
    63.00
     Prototype
    62.25
    Prototype
    59.75
    Prot
    57.75
    prot
    57.50
    Activations Density 0.069%

    No Known Activations